newmediamonitoring/敏感词查找_weibo.py

39 lines
1.4 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import csv
import os
file_path = "D:/2021/新媒体/1月份10-20weibo/1月份10-20weibo"
path = os.listdir(file_path)
def get_weibo_cuominzi(cuominzi):
with open('D:/2021/新媒体/weibo错敏字3.csv','w', newline='',encoding='utf-8') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(
[ "错敏字","id","文章url", "发布时间","位置"])
for file in path:
f_p = os.listdir(file_path+'/'+file)
for f in f_p:
with open(file_path+'/'+file + '/'+f,encoding='utf8') as csvfile:
reader_wb = csv.reader(csvfile)
for r_w in reader_wb:
for c in cuominzi:
print(c)
if str(c[0]) in str(r_w[1]):
print(str(r_w[1]).index(str(c[0])))
writer.writerow([c[0], r_w[0], r_w[2], r_w[8],
str(r_w[1])[str(r_w[1]).index(str(c[0])) - 10:str(r_w[1]).index(str(c[0])) + 10]])
else:
print(r_w[1])
if __name__ == '__main__':
cuominzi = []
with open('D:/2021/新媒体/错敏字.csv') as csvfile:
reader = csv.reader(csvfile)
for r in reader:
if r[0] != '错敏字' and r[0] != '':
cuominzi.append(r)
print(cuominzi)
get_weibo_cuominzi(cuominzi)